用小数据提升大模型在专业领域术语翻译的准确性
Efficient Terminology Integration for LLM-based Translation in Specialized Domains
- 用字典树提取术语并重建训练数据，让大模型学会专业术语
- 在WMT专利翻译任务中表现最优，术语翻译准确率显著提升
- 适合需要术语一致性的专利、医药、金融等专业场景
传统机器翻译通常直接在大规模平行语料上训练模型，对专业术语关注不足。在专利、金融或生物医学等领域，术语翻译必须遵循既定规范，一致性至关重要。本文提出一种高效方法，仅需少量数据即可提升大模型对专业术语的翻译能力。通过字典树算法系统提取术语并构建术语表，再重构训练数据，使大模型学习如何正确集成这些术语。该方法显著增强了模型处理专业术语的能力，确保高质量翻译。在WMT专利翻译任务中，本方法取得当前最高得分，验证了其在通用方法难以胜任的专业翻译领域的有效性与普适性。
原文摘要 · Abstract (English)
Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In specialized fields such as patent, finance, or biomedical domains, terminology is crucial for translation, with many terms that needs to be translated following agreed-upon conventions. In this paper we introduce a methodology that efficiently trains models with a smaller amount of data while preserving the accuracy of terminology translation. We achieve this through a systematic process of term extraction and glossary creation using the Trie Tree algorithm, followed by data reconstruction to teach the LLM how to integrate these specialized terms. This methodology enhances the model's ability to handle specialized terminology and ensures high-quality translations, particularly in fields where term consistency is crucial. Our approach has demonstrated exceptional performance, achieving the highest translation score among participants in the WMT patent task to date, showcasing its effectiveness and broad applicability in specialized translation domains where general methods often fall short.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。